Digital Behaviour Change Interventions (DBCIs) aim at improving individual health by engaging various means of Information and Communication Technology (ICT), including mobile apps and wearables. Participant intervention fatigue may happen when DBCIs become too frequent, repetitive, demanding, or lack perceived relevance, and this may result in participants' reduced motivation and adherence over time. Advancing technology-supported engagement mechanisms is therefore of utmost importance. To address this problem, we present a reference and solution architecture based on open-source technologies and open Application Programming Interfaces (Open APIs). First, we integrated a Large Language Model (LLM) component into the DBCI design. Second, to support context-awareness, we enhanced this integration by adding a Geographic Information Systems (GIS) element. Our pilot implemented AI4Motion platform targets both personalization and contextualization aspects of DBCIs. Our work contributes to the emerging discussion on LLM/GIS-related system design patterns for digital platforms supporting Ecological Momentary Assessment (EMA), Experience Sampling Method (ESM), and Just-in-Time Adaptive Interventions (JITAIs).

Consumer Health Informatics Lab Department of Information Technology Prague University of Economics and Business Prague Czech Republic

Department of Geography Masaryk University Brno Czech Republic

Department of Human Movement Studies University of Ostrava Ostrava Czech Republic

Zobrazit více v PubMed

Sucala M, Ezeanochie NP, Cole-Lewis H, Turgiss J (2020) An iterative, interdisciplinary, collaborative framework for developing and evaluating digital behavior change interventions. Transl Behav Med 10:1538–1548.10.1093/tbm/ibz109 PubMed PMC

Arigo D, Jake-Schoffman DE, Pagoto SL (2025) The recent history and near future of digital health in the field of behavioral medicine: an update on progress from 2019 to 2024. J Behav Med 48:120–136. 10.1007/s10865-024-00526-x PubMed PMC

Willms A, Rush J, Hofer S et al (2025) Advancing physical activity research methods using real-time and adaptive technology: A scoping review of “no-code” mobile health app research tools. Sport Exerc Perform Psychol 14:250–267. 10.1037/spy0000360

Meywirth S (2024) Designing a Large Language Model-Based Coaching Intervention for Lifestyle Behavior Change. In: International Conference on Design Science Research in Information Systems and Technology (DESRIST). pp 81–94.

Schwarz A, Winkens LHH, de Vet E, et al. (2023) Design Features Associated With Engagement in Mobile Health Physical Activity Interventions Among Youth: Systematic Review of Qualitative and Quantitative Studies. JMIR Mhealth Uhealth 11:e40898.10.2196/40898 PubMed PMC

Stade EC, Stirman SW, Ungar LH, et al. (2024) Large language models could change the future of behavioral healthcare: a proposal for responsible development and evaluation. npj Mental Health Research 3:.10.1038/s44184-024-00056-z PubMed PMC

Barber BV, Kephart G, Martin-Misener R, et al. (2024) Integrating health geography and behavioral economic principles to strengthen context-specific behavior change interventions. Transl Behav Med 14:257–272.10.1093/tbm/ibad065 PubMed PMC

Tobin K, Heidari O, Volpi C, et al. (2023) Use of geofencing interventions in population health research: a scoping review. BMJ Open 13:.10.1136/bmjopen-2022-069374 PubMed PMC

Chen B, Dethlefs N (2025) ProactiMate: Evaluating LLM-Based Chatbots for Behavior Change Interventions. To appear in Computational Intelligence.10.22541/au.174807396.68998051/v1

Willms A, Liu S (2024) Exploring the Feasibility of Using ChatGPT to Create Just-in-Time Adaptive Physical Activity mHealth Intervention Content: Case Study. JMIR Med Educ 10:e51426. 10.2196/51426 PubMed PMC

Hegde N, Vardhan M, Nathani D, et al. (2024) Infusing behavior science into large language models for activity coaching. PLOS Digital Health 3:.10.1371/journal.pdig.0000431 PubMed PMC

Haag D, Kumar D, Gruber S, et al. (2025) The Last JITAI? Exploring Large Language Models for Issuing Just-in-Time Adaptive Interventions: Fostering Physical Activity in a Prospective Cardiac Rehabilitation Setting. In: Conference on Human Factors in Computing Systems (CHI). pp 1–18.

Muroň M, Dařena F, Procházka D, Kern R (2025) Automatically generated place descriptions for accurate location identification: a hybrid approach with rule-based methods and LLM. Spat Cogn Comput .10.1080/13875868.2025.2449859

Wu C, Lin W, Zhang X et al (2024) PMC-LLaMA:Toward building open-source language models for medicine. Journal of the American Medical Informatics Association 31:1833–1843. 10.1093/jamia/ocae045 PubMed PMC

Janek M, Kuhnova J, Cardon G, et al. (2025) Ecological momentary assessment of physical and eating behaviours: The WEALTH feasibility and optimisation study with recommendations for large-scale data collection. PLoS One 20:.10.1371/journal.pone.0318772 PubMed PMC